Frontiers

Using reinforcement learning in genome assembly: in-depth analysis of a Q-learning assembler

Genome assembly remains an unsolved problem, and de novo strategies (i.e., those run without a reference) are relevant but computationally complex tasks in genomics. Although de novo assemblers have ...
eLife

Q-learning with temporal memory to navigate turbulence

This important study uses reinforcement learning to study how turbulent odor stimuli should be processed to yield successful navigation. The authors find that there is an optimal memory length over ...
GitHub

Calvano Q-learning Oligopoly Simulation

A high-fidelity Python implementation of the Q-learning oligopoly simulation from Calvano et al. (2020). This project provides a complete, tested, and extensible reproduction of the seminal study ...
Scientific Research Publishing

Kumar, A., Zhou, A., Tucker, G. and Levine, S. (2020) Conservative Q-Learning for Offline Reinforcement Learning. Advances in Neural Information Processing Systems, 33, 1179-1191.

ABSTRACT: Offline reinforcement learning (RL) focuses on learning policies using static datasets without further exploration. With the introduction of distributional reinforcement learning into ...
Frontiers

Hybrid genetic algorithm and Q-learning-based solution for the time-variant berth and quay crane allocation problem

Institute of Logistics Science and Engineering of Shanghai Maritime University, Pudong, China Introduction: This study addresses the joint scheduling optimization of continuous berths and quay cranes ...
marktechpost

Google DeepMind Achieves State-of-the-Art Data-Efficient Reinforcement Learning RL with Improved Transformer World Models

Reinforcement Learning RL trains agents to maximize rewards by interacting with an environment. Online RL alternates between taking actions, collecting observations and rewards, and updating policies ...
IEEE

Q-Learning Methods for LQR Control of Completely Unknown Discrete-Time Linear Systems

Abstract: This paper focuses on solving the linear quadratic regulator problem for discrete-time linear systems without knowing system matrices. The classical Q-learning methods for linear systems can ...